© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8220
    Prev
    Next
    INDEX
    Explanations

    listing ways, minutes, samples, miles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸Ģéĥ¨åĪĨ
    -0.11
    çļĦä¸Ģ款
    -0.11
    è¿Ļéĥ¨åĪĨ
    -0.11
    æĽ´å¤ļä¿¡æģ¯
    -0.10
    çĽ¸ä¿¡å¤§å®¶
    -0.10
    æľ¬è½®
    -0.09
    çļĦä¸ĢéĿ¢
    -0.09
    éĥ¨åĪĨåĨħ容
    -0.09
    æĺ¯æľĢ好çļĦ
    -0.09
    illions
    -0.09
    POSITIVE LOGITS
    çIJ¯
    0.09
    缸继
    0.09
    æ§
    0.09
    eus
    0.08
    æŃ¥éª¤
    0.08
     conspir
    0.08
     Fry
    0.08
    axes
    0.07
    less
    0.07
    éŃĤ
    0.07
    Activations Density 0.404%

    No Known Activations